Back to EveryPatent.com
United States Patent | 6,230,122 |
Wu ,   et al. | May 8, 2001 |
A method for effectively suppressing background noise in a speech detection system comprises a filter bank for separating source speech data into discrete frequency sub-bands to generate filtered channel energy, and a noise suppressor for weighting the frequency sub-bands to improve the signal-to-noise ratio of the resultant noise-suppressed channel energy. The noise suppressor preferably includes a subspace module for using a Karhunen-Loeve transformation to create a subspace based on the background noise, a projection module for generating projected channel energy by projecting the filtered channel energy onto the created subspace, and a weighting module for applying calculated weighting values to the projected channel energy to generate the noise-suppressed channel energy.
Inventors: | Wu; Duanpei (Sunnyvale, CA); Tanaka; Miyuki (Campbell, CA); Amador-Hernandez; Mariscela (San Jose, CA) |
Assignee: | Sony Corporation (Tokyo, JP); Sony Electronics Inc. (Park Ridge, NJ) |
Appl. No.: | 176178 |
Filed: | October 21, 1998 |
Current U.S. Class: | 704/226; 704/204; 704/233 |
Intern'l Class: | G10L 021/02 |
Field of Search: | 704/233,226,227,204 |
4592085 | May., 1986 | Watari et al. | 381/43. |
4630304 | Dec., 1986 | Borth et al. | 381/94. |
4910716 | Mar., 1990 | Kirlin et al. | 367/24. |
4951266 | Aug., 1990 | Hsu et al. | 367/25. |
5003601 | Mar., 1991 | Watari et al. | 381/43. |
5093899 | Mar., 1992 | Hiraiwa | 395/23. |
5212764 | May., 1993 | Ariyoshi | 704/233. |
5301257 | Apr., 1994 | Tani | 395/11. |
5485524 | Jan., 1996 | Kuusama et al. | 381/94. |
5513298 | Apr., 1996 | Stanford et al. | 395/2. |
5615296 | Mar., 1997 | Stanford et al. | 395/2. |
5699480 | Dec., 1997 | Martin | 704/205. |
5715367 | Feb., 1998 | Gillick et al. | 395/2. |
5806025 | Sep., 1998 | Vis et al. | 704/226. |
Haykin, Simon, "Neural Networks," 1994, pp. 363-370. Ephraim et al., A Signal Subspace Approach For Speech Enhancement, Jul. 1995, pp. 251-266 IEEE Trans. Speech and Audio Proc., vol. 3 Iss.4. Lee et al., Image Enhancement Based On Signal Subspace Approach, Aug. 1999, pp 1129-1134, IEEE Trans. Image Proc., vol. 8, Iss.8. Ephraim et al., A Spectrally-Based Signal Subspace Approach For Speech Enhancement, May 1995, pp 804-807, 1995 Int. Conf. Acoust. Speech Sig. Proc., ICASSP-95, vol. 1. |